metadata
license: apache-2.0
tags:
- summarization
- generated_from_trainer
metrics:
- rouge
model-index:
- name: t5-base-news_headlines
results: []
t5-base-news_headlines
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1569
- Rouge1: 50.0083
- Rouge2: 29.6819
- Rougel: 46.8393
- Rougelsum: 46.8438
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5.6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 1.9951 | 1.0 | 1531 | 1.5057 | 44.519 | 22.4497 | 40.7613 | 40.7478 |
| 1.6093 | 2.0 | 3062 | 1.3058 | 46.2567 | 24.5777 | 42.6763 | 42.6283 |
| 1.4268 | 3.0 | 4593 | 1.2573 | 47.8969 | 27.011 | 44.4848 | 44.4922 |
| 1.3068 | 4.0 | 6124 | 1.1890 | 49.6078 | 29.1636 | 46.314 | 46.3458 |
| 1.2354 | 5.0 | 7655 | 1.1569 | 50.0083 | 29.6819 | 46.8393 | 46.8438 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3